tomz

#!/bin/bash -ex

# Install Git
sudo yum -y install git

# Install Maven
wget -P /tmp http://apache.mirrors.spacedump.net/maven/maven-3/3.3.3/binaries/apache-maven-3.3.3-bin.tar.gz
sudo mkdir /opt/apache-maven
sudo tar -xvzf /tmp/apache-maven-3.3.3-bin.tar.gz -C /opt/apache-maven

tomz

# If you are using Spark 1.4, then launch SparkR with the command
#
# ./bin/sparkR --packages com.databricks:spark-csv_2.10:1.0.3
# as the `sparkPackages=` flag was only added in Spark 1.4.1.

# # This will work in Spark 1.4.1. 
sc <- sparkR.init(spark_link, sparkPackages = "com.databricks:spark-csv_2.10:1.0.3") 
sqlContext <- sparkRSQL.init(sc) 

flights <- read.df(sqlContext, "s3n://sparkr-data/nycflights13.csv","com.databricks.spark.csv", header="true")

tomz

Sys.setenv(SPARK_HOME="/Users/shivaram/spark-1.4.1")
.libPaths(c(file.path(Sys.getenv("SPARK_HOME"), "R", "lib"), .libPaths()))
library(SparkR)
sc <- sparkR.init(master="local")
sqlContext <- sparkRSQL.init(sc)

df <- createDataFrame(sqlContext, faithful)
# Select one column
head(select(df, df$eruptions))

tomz

sudo wget http://repos.fedorapeople.org/repos/dchen/apache-maven/epel-apache-maven.repo -O /etc/yum.repos.d/epel-apache-maven.repo
sudo sed -i s/\$releasever/6/g /etc/yum.repos.d/epel-apache-maven.repo
sudo yum install -y apache-maven
mvn --version

tomz

cd ~
sudo apt-get update
sudo apt-get install openjdk-7-jre-headless -y


### Check http://www.elasticsearch.org/download/ for latest version of ElasticSearch and replace wget link below

# NEW WAY / EASY WAY
wget https://download.elasticsearch.org/elasticsearch/elasticsearch/elasticsearch-0.90.2.deb
sudo dpkg -i elasticsearch-0.90.2.deb

tomz

# Documentation for HAProxy
#   http://code.google.com/p/haproxy-docs/w/list
#   http://haproxy.1wt.eu/download/1.2/doc/architecture.txt

# NOTES:
#   open files limits need to be > 256000, use ulimit -n to set (on most POSIX systems)

global
        log 127.0.0.1     local0
        log 127.0.0.1     local1 notice